Agent Maturity Compass API - v1.2.0
    Preparing search index...

    Interface JudgeResult

    interface JudgeResult {
        judgeId: string;
        judgePrompt: string;
        mode: "llm" | "simulated";
        model: string;
        rawScore: number;
        reasoning: string;
        rubricLevel: string;
        score: number;
        templateId: string;
        templateName: string;
        timestamp: number;
    }
    Index
    judgeId judgePrompt mode model rawScore reasoning rubricLevel score templateId templateName timestamp
    judgeId: string
    judgePrompt: string

    The full judge prompt that was/would be sent

    mode: "llm" | "simulated"

    Whether this was evaluated by an actual LLM or simulated

    model: string

    Model used for judgment

    rawScore: number

    Raw score on the rubric scale

    reasoning: string

    The reasoning provided by the judge

    rubricLevel: string

    Which rubric level was matched

    score: number

    Normalized score (0-1)

    templateId: string
    templateName: string
    timestamp: number

    Settings
    Member Visibility

    On This Page
    Properties